AI code review for GitHub
PURA reviews every pull request on GitHub automatically. Add as many developers as you like at a fixed price, choose which AI models review your code, and set a budget for each team so you always know what you'll spend.
1-month free trial · bring your own keys · we never store your code
Why PURA
Seat licences, a model someone else picked, and one spending cap for everyone. PURA replaces all three.
01
Every developer and every team gets AI review on every plan. You pay for the reviews you run, so hiring never raises the bill.
Instead ofpaying a seat fee for every developer
Saved per year
$10,000
02
A database, servers and a few engineer hours a month already cost more than PURA, before anyone writes review logic. Keep your engineers on your product.
Instead ofbuilding and running your own reviewer
Saved per year
$4,600
03
Choose the model for the whole org, a single team or a kind of change. Try a new model on part of your pull requests, switch when it proves itself, and keep your strongest model for security-sensitive code.
Instead ofa vendor choosing the model for you
04
Give each contributing team, reviewing team, author or repo its own daily, weekly or monthly budget. Connect one API key and PURA enforces them all. When a budget is reached, PURA pauses those reviews until it resets.
Instead ofone spending cap shared by everyone
How it works
Install the GitHub App and connect your Anthropic, OpenAI, Google or OpenAI-compatible provider key.
Create review agents: pick their models and set budgets per team, author or repo.
Open a pull request. PURA reviews it automatically, and again on every new commit, posting a summary, findings ranked by severity, and fixes you can apply. Comment /pura review to run it on demand.
And more
Not only PR review: PURA also checks PR quality. It reviews titles, descriptions, labels and commit messages, so every pull request meets your team’s standard.
Each review agent follows its own SKILL.md in your repo: what to look for, what to ignore, and which model to use, written in plain English.
Give reviewers your own skills, such as a security checklist or your API conventions, shared from one repository across all of them.
Pricing
One fee per plan, based on the number of reviews. No per-seat fees. Compare it against per-seat pricing.
For a team getting AI review under control.
For growing orgs reviewing across many repos.
For larger orgs that need depth and priority support.
For security, scale, and procurement needs.
You bring your own AI provider keys, so inference is billed by your provider, never marked up by PURA. Prices exclude VAT.
Schedule a demo
Bring the questions your CTO, security lead or finance partner will ask. In 30 minutes we'll show the product, the controls and the numbers.
FAQ
PURA charges a flat platform fee per plan, metered by the number of reviews, with no per-seat fees and no hidden charges. You bring your own model API keys and pay your AI provider directly for inference. PURA never marks it up.
No. Contributors, repositories and teams are unlimited on every plan. Only the number of reviews moves the price. Try the RoI calculator with your own team size and PR volume.
Yes. PURA is a GitHub App. It reviews every pull request when it is opened, marked ready for review or updated with new commits, and posts one review in GitHub: a summary, findings ranked by severity, and fixes you can apply. Comment /pura review to run a review at any time.
Yes. PURA is bring-your-own-key: connect your own Anthropic, OpenAI, Google (Gemini) or OpenAI-compatible provider account, and inference is billed directly by that provider with no markup. Your keys are encrypted at rest and never shown again after you save them.
Set daily, weekly and monthly budgets per agent and provider, and per contributing team, reviewing team, author, repo or pull request. When a budget is reached, PURA pauses those reviews until it resets. The dashboard shows where every dollar goes.
You decide. Write routing rules in plain English in a review skill so PURA sends sensitive changes (like payments or auth) to premium models and routine changes (like docs or dependency bumps) to cheaper ones.
No. Code is processed transiently to generate a review and is not retained afterward, and detected secrets are redacted before anything is sent to the model. PURA does not use your source code to train AI models.
No. PURA's reviews are advisory and assist your team. You stay in control of every merge and release decision.